Deep learning algorithms for predicting renal replacement therapy initiation in CKD patients: a retrospective cohort study.

BACKGROUND: Chronic kidney disease (CKD) requires accurate prediction of renal replacement therapy (RRT) initiation risk. This study developed deep learning algorithms (DLAs) to predict RRT risk in CKD patients by incorporating medical history and prescriptions in addition to biochemical investigations. METHODS: A multi-centre retrospective cohort study was conducted in three major hospitals in Hong Kong. CKD patients with an eGFR < 30ml/min/1.73m2 were included. DLAs of various structures were created and trained using patient data. Using a test set, the DLAs' predictive performance was compared to Kidney Failure Risk Equation (KFRE). RESULTS: DLAs outperformed KFRE in predicting RRT initiation risk (CNN + LSTM + ANN layers ROC-AUC = 0.90; CNN ROC-AUC = 0.91; 4-variable KFRE: ROC-AUC = 0.84; 8-variable KFRE: ROC-AUC = 0.84). DLAs accurately predicted uncoded renal transplants and patients requiring dialysis after 5 years, demonstrating their ability to capture non-linear relationships. CONCLUSIONS: DLAs provide accurate predictions of RRT risk in CKD patients, surpassing traditional methods like KFRE. Incorporating medical history and prescriptions improves prediction performance. While our findings suggest that DLAs hold promise for improving patient care and resource allocation in CKD management, further prospective observational studies and randomized controlled trials are necessary to fully understand their impact, particularly regarding DLA interpretability, bias minimization, and overfitting reduction. Overall, our research underscores the emerging role of DLAs as potentially valuable tools in advancing the management of CKD and predicting RRT initiation risk.

Tacrolimus versus mycophenolate mofetil for induction therapy of lupus nephritis: a randomised controlled trial and long-term follow-up.

OBJECTIVE: To compare the efficacy of tacrolimus (TAC) and mycophenolate mofetil (MMF) for the initial therapy of lupus nephritis (LN). STUDY DESIGN: This is an open randomised controlled parallel group study. METHODS: Adult patients with biopsy-confirmed active LN (class III/IV/V) were randomised to receive prednisolone (0.6 mg/kg/day for 6 weeks and tapered) in combination with either TAC (0.06-0.1 mg/kg/day) or MMF (2-3 g/day) for 6 months. Good responders were shifted to azathioprine for maintenance. The primary outcome was the rate of complete renal response (CR) at 6 months and the secondary outcomes included partial renal response, renal flares and decline of renal function over time. RESULTS: 150 patients (92% women; aged 35.5±12.8 years; 81% class III/IV) were randomised (76 MMF, 74 TAC). At month 6, the rate of CR was 59% in the MMF and 62% in the TAC group (treatment difference: 3.0% (-12%, 18%); p=0.71). Major infective episodes occurred in 9.2% patients treated with MMF and in 5.4% patients treated with TAC (p=0.53). Maintenance therapy with azathioprine was given to 79% patients. After 60.8±26 months, proteinuric and nephritic renal flares developed in 24% and 18% of patients in the MMF group and 35% (p=0.12) and 27% (p=0.21) in the TAC group, respectively. The cumulative incidence of a composite outcome of decline of creatinine clearance by ≥30%, development of chronic kidney disease stage 4/5 or death was 21% in the MMF and 22% in the TAC group of patients (p=0.35). CONCLUSIONS: TAC is non-inferior to MMF, when combined with prednisolone, for induction therapy of active LN. With azathioprine maintenance for 5 years, a non-significant trend of higher incidence of renal flares and renal function decline is observed with the TAC regimen. TRIAL REGISTRATION NUMBER: Hospital Authority Research Ethics Committee Clinical Trial Registry (HARECCTR0500018; Hong Kong) and US ClinicalTrials.gov (NCT00371319).

The use of enteric-coated mycophenolate sodium in the treatment of relapsing and steroid-dependent minimal change disease.

We report on the successful treatment of 5 consecutive adult patients with steroid-dependent or frequently relapsing minimal change disease (MCD), using a regimen of enteric-coated mycophenolate sodium (E-MPS) and prednisolone. E-MPS was used for induction therapy in 3 patients, and maintenance therapy in 2, all in conjunction with steroid treatment in tapering doses. Eventually 4 patients managed to discontinue steroid treatment, and 2 of them were also withdrawn from E-MPS. This combination therapy resulted in sustained remission and was well tolerated by our patients, with no signs of gastrointestinal upset, marrow suppression or increased incidence of infections. Our preliminary experience suggests that E-MPS is a promising new alternative in the management of steroid-dependent and relapsing MCD with a possibility of improving gastrointestinal tolerance.

Risk and predictors of arterial thrombosis in lupus and non-lupus primary glomerulonephritis: a comparative study.

We conducted the current study to compare the incidence and risk factors of arterial thrombosis in lupus and non-lupus primary glomerulonephritis. We identified patients in whom lupus nephritis and non-lupus primary glomerulonephritis were diagnosed between 1993 and 2003 using our lupus cohort database and pathology registry. We analyzed the cumulative incidence of new arterial thromboembolic events since diagnosis by Kaplan-Meier plot, and studied risk factors by multivariate analysis. We studied 162 patients with lupus and 181 patients with non-lupus primary glomerulonephritis. After a mean observation of 8.1 years, 47 (14%) patients died, 23 (7%) were lost to follow-up, and 38 (11%) developed 42 arterial events (incidence, 15.1/1000 patient-years). Although patients with lupus nephritis were younger and had a significantly lower frequency of smoking, hypertension, obesity, and renal dysfunction, their cumulative risk of arterial event at 5 years was not significantly lower than that of patients with primary non-lupus glomerulonephritis (6.3% vs. 6.6%, p = 0.96). In a Cox regression model, lupus was found to be an independent risk factor for arterial thrombosis (hazard ratio 3.57 [1.07-11.9]; p = 0.04), in addition to increasing age (hazard ratio 1.04 per year; p = 0.02), low-density lipoprotein > or =2.6 mmol/L (hazard ratio 4.46; p = 0.002), and glomerular filtration rate <30 mL/min (hazard ratio 2.67; p = 0.04). We concluded that in immune-mediated glomerulonephritis, having systemic lupus increased the risk of arterial thromboembolism after adjustment for age, renal insufficiency, and other traditional risk factors.

Use of allopurinol in slowing the progression of renal disease through its ability to lower serum uric acid level.

BACKGROUND: Hyperuricemia is associated strongly with the development of hypertension, renal disease, and progression. Allopurinol decreases serum uric acid levels by inhibiting the enzyme xanthine oxidase. We hypothesized that administrating allopurinol to decrease serum uric acid levels to the normal range in hyperuricemic patients with chronic kidney disease may be of benefit in decreasing blood pressure and slowing the rate of renal disease progression in these patients. METHODS: We conducted a prospective, randomized, controlled trial of 54 hyperuricemic patients with chronic kidney disease. Patients were randomly assigned to treatment with allopurinol, 100 to 300 mg/d, or to continue the usual therapy for 12 months. Clinical, hematologic, and biochemical parameters were measured at baseline and 3, 6, and 12 months of treatment. We define our study end points as: (1) stable kidney function with less than 40% increase in serum creatinine level, (2) impaired renal function with creatinine level increase greater than 40% of baseline value, (3) initiation of dialysis therapy, and (4) death. RESULTS: One patient in the treatment group dropped out because of skin allergy to allopurinol. Serum uric acid levels were significantly decreased in subjects treated with allopurinol, from 9.75 +/- 1.18 mg/dL (0.58 +/- 0.07 mmol/L) to 5.88 +/- 1.01 mg/dL (0.35 +/- 0.06 mmol/L; P < 0.001). There were no significant differences in systolic or diastolic blood pressure at the end of the study comparing the 2 groups. There was a trend toward a lower serum creatinine level in the treatment group compared with controls after 12 months of therapy, although it did not reach statistical significance (P = 0.08). Overall, 4 of 25 patients (16%) in the allopurinol group reached the combined end points of significant deterioration in renal function and dialysis dependence compared with 12 of 26 patients (46.1%) in the control group (P = 0.015). CONCLUSION: Allopurinol therapy significantly decreases serum uric acid levels in hyperuricemic patients with mild to moderate chronic kidney disease. Its use is safe and helps preserve kidney function during 12 months of therapy compared with controls. Results of this study need to be confirmed with an additional prospective trial involving a larger cohort of patients to determine the long-term efficacy of allopurinol therapy and in specific chronic kidney disease subpopulations.

Use of intraperitoneal urokinase for resistant bacterial peritonitis in continuous ambulatory peritoneal dialysis.

Intraperitoneal (IP) urokinase is a fibrinolytic agent that has been used in the adjunctive treatment of continuous ambulatory peritoneal dialysis (CAPD) and resistant and relapsing peritonitis. However, its efficacy and role in treating resistant CAPD bacterial peritonitis remain unclear and results from previous prospective studies have been conflicting. We prospectively randomized 88 CAPD patients with bacterial peritonitis resistant to initial empirical IP antibiotics into two groups: IP urokinase 60,000 IU and a placebo group. Patients were treated concomitantly with susceptible antibiotics according to culture results. Peritoneal dialysate grew pseudomonas aeruginosa in 13 patients (14.8%), non-pseudomonas bacteria in 63 patients (71.6%) and negative cultures in 12 patients (13.6%). For the clinical outcomes, there were no significant differences in the primary response rates (61.4 vs. 50%), relapse rates (9.1 vs. 13.6%), Tenckhoff catheter removal rates (22.7 vs. 29.5%) and mortality rates (6.8 and 6.8%) between the urokinase group and the controls (p=ns). Subgroup analysis of culture negative patients (n=12) also demonstrated no sgnificant benefit for urokinase treatment. No significant adverse effects were encountered with the IP urokinase instillation. Total median peritonitis-related length of hospitalization for the urokinase group and controls were 7 and 11 days, respectively (p=0.32). We concluded that IP urokinse plays no significant role as an adjuvant therapy in the treatment of bacterial CAPD peritonitis resistant to initial IP antibiotic therapy.

Haemodialysis catheter-related right transverse cervical artery pseudoaneurysm and treatment by coil embolization.

In patients with end-stage renal disease, temporary placement of venous catheters for haemodialysis (HD) is often necessary, and the right internal jugular (RIJ) vein is the usual preferred site of HD catheter placement. We report here a patient who experienced complications because of the development of a pseudoaneurysm of the transverse cervical artery following an apparently uneventful RIJ vein cannulation for temporary HD, using the blind landmark-guided technique. This is a rare complication of RIJ vein cannulation and HD catheter placement. The pseudoaneurysm presented 3 weeks after the procedure and was diagnosed by using colour-Doppler ultrasound, followed by an angiogram, and it was successfully occluded using endovascular coil embolization.

Tacrolimus for induction therapy of diffuse proliferative lupus nephritis: an open-labeled pilot study.

BACKGROUND: Tacrolimus is a relatively new calcineurin inhibitor that has been increasingly used in transplant medicine. The objective of the current work is to report our preliminary experience with tacrolimus in the treatment of diffuse proliferative glomerulonephritis in systemic lupus erythematosus (SLE). METHODS: Nine consecutive patients who fulfilled the American College of Rheumatology criteria for SLE and with biopsy-proven diffuse proliferative glomerulonephritis were recruited for an open-labeled trial with prednisolone and oral tacrolimus (0.1 mg/kg/day for 2 months, followed by 0.06 mg/kg/day). Prospective data on renal response and serologic lupus activity were collected. The efficacy and safety of this regimen was reported. RESULTS: Baseline characteristics of the patients were: mean age 33.3 +/- 12 years, women to men ratio 2:1, serum creatinine 94.2 +/- 46 micromol/L, daily proteinuria 4.56 +/- 2.4 g, seven (78%) patients were nephrotic, three (33%) were hypertensive, and four (44%) had elevated serum creatinine at the time of renal biopsy. At 6 months of therapy, complete and partial renal response was achieved in six (67%) and two (22%) patients, respectively. Significant improvement in proteinuria, hemoglobin, serum albumin, and C3 levels was observed in comparison with baseline values, starting at the second month. Tacrolimus was generally well tolerated, except for two patients who developed transient hyperglycemia. Infective complications, amenorrhea, hypertrichosis, gingivitis, new-onset hypertension, and significant increase in serum creatinine were not reported. CONCLUSION: Tacrolimus is an effective option for induction treatment of SLE-diffuse proliferative glomerulonephritis. Further trials are necessary to determine the optimal dosage and duration of therapy, and its efficacy in comparison to standard regimens.

Fatal case of Aspergillus coinfection in a renal transplant recipient suffering from cytomegalovirus pneumonitis.

Cytomegalovirus (CMV) disease is common in postrenal transplant recipients, and may predispose the patients to secondary bacterial or fungal infections. However, simultaneous coinfection is rare and often makes diagnosis difficult. We report a case of CMV pneumonitis in a renal transplant recipient presenting with elevated CMV pp65 antigen level and abnormal chest radiograph. Despite potent and broad-spectrum antimicrobial therapy, his condition deteriorated rapidly - he soon went into respiratory failure, septic shock and died several days later. Transbronchial biopsy and bronchoalveolar lavage obtained before the patient's death showed evidence of invasive pulmonary aspergillosis with concomitant CMV pneumonitis. High index of suspicion and early and empirical initiation of antifungal therapy may be necessary for successful management of fulminant pneumonia in solid organ transplant recipients.

Clinical outcomes of systemic lupus erythematosus patients undergoing continuous ambulatory peritoneal dialysis.

OBJECTIVES: The purpose of this study was to evaluate the outcome of systemic lupus erythematosus (SLE) patients on continuous ambulatory peritoneal dialysis (CAPD). METHODS: Eighteen SLE patients who had been undergoing CAPD for at least 3 months in our unit were compared with 36 other age- and gender-matched non-diabetic CAPD patients with an underlying primary chronic glomerulonephritis (CGn). The clinical outcome, infective complications, lupus activities, biochemical parameters, haemoglobin level and the use of erythropoietin were reviewed. RESULTS: The duration of dialysis of the two studied groups was not different, with a mean of 35.4 months for the SLE group and 36.7 months for the CGn group. Before dialysis, SLE patients had a significantly lower albumin level (30.4+/-6.6 vs 35.4+/-5.59 g/dl, P<0.01), while the mean haemoglobin levels of the two groups were similar (8.5+/-1.8 g/dl for SLE vs 9.0+/-1.9 g/dl for the control group). However, the weekly dose of erythropoietin (EPO) used was significantly higher in the SLE group (6000 vs 3818 U/week, P<0.01) to maintain a similar haemoglobin level during dialysis. Regarding the infective complications, the SLE group had a higher peritonitis rate (5.7 episodes/100 patient-months vs 2.4 episodes/100 patient-months, P<0.05), and an increase in the non catheter related infection rate (6.67 episodes/100 patient-months vs 1.1 episodes/100 patient-months, P<0.001). However, no significant difference could be demonstrated in the Tenckhoff catheter exit site infection rate (2 episodes/100 vs 1.7 episode/100 patient-months). The number of patients who received a kidney transplant or required a change of mode to haemodialysis was similar among the two groups. Seven patients died during the follow-up period, and the overall mortality rate was much higher in the SLE group than in the control group (0.83/100 vs 0.15/100 patient-months, P<0.05). CONCLUSIONS: SLE patients on CAPD have a significantly lower pre-dialysis serum albumin level and use a higher dose of Epo to achieve a comparable haemoglobin level than other non-diabetic CGn CAPD patients. They also have a poorer prognosis in terms of infective complications and mortality rate.

Ultrasonography in the management of exit site infections in peritoneal dialysis patients.

AIM: To assess the efficacy of using ultrasonography (USG) in monitoring the progress of exit site infection (ESI) in patients undergoing continuous ambulatory peritoneal dialysis (CAPD). METHODS: Twenty-two cases of newly diagnosed ESI and 20 cases with normal exit sites as controls were assessed by using USG. The exit sites were reassessed by using USG after finishing a course of antibiotic therapy, and the sonographic findings were correlated with the clinical outcome. RESULTS: Out of the 22 cases of ESI, 21 cases had definite sonolucent zones around the external cuffs, while one case had normal sonographic findings. Of the 20 control cases of normal exit sites, 16 had normal sonographic findings, and four had sonolucent zones around the external cuffs. Exit site infections correlated with positive sonographic findings as compared to normal exits (P <0.0001). The 21 cases of ultrasonic-positive ESI were re-examined after antibiotic therapy, and 10 of these had a post-treatment sonolucent rim around the distal cuff < or =1 mm thick, while 11 cases were persistently > mm thick. The former group was shown to have a more favourable outcome (P=0.013). And despite variable USG findings, all eight patients with Pseudomonas aeruginosa-related ESI had an unfavourable clinical outcome. CONCLUSION: Ultrasonography of the exit sites in CAPD patients is a useful adjunctive tool in the management of ESI. A sonolucent zone around the external cuff >1 mm thick following a course of antibiotic treatment and the involvement of the proximal cuff are associated with poor clinical outcome. In ESI caused by Pseudomonas aeruginosa, the clinical outcome was uniformly poor irrespective of the sonographic findings.